AI Red Team Specialist – Lead Researcher in Agentic Security →

Cph Ai Hub; København; Hybride; DKK 900 000 - 1 300 000; Plein temps

Avantages offerts par ce poste

Competitive salary

Bonus package

Training & conferences

Remote work with Copenhagen office

Résumé du poste

The Tech Collective is seeking an experienced red team professional to join our advanced product and research team in Copenhagen. You will build and evolve a tool that dynamically tests LLMs and their agent contexts for vulnerabilities, collaborating with reverse engineers, pentesters and data scientists to harden client workloads.

You will own and develop modules for testing the application context, including API security and misconfigurations, while contributing to vulnerability research and

Qualifications

• Minimum five years’ progressive experience in enterprise red teaming or offensive research.
• Strong track record in web application pentesting with emphasis on remediation and hardening.
• Experience defining and driving product roadmaps for red team tools (valued).

Responsabilités

• Own and develop product modules for testing the application context (API security, cryptographic implementation, broken authentication, RBAC).
• Develop and refine a dynamic red-team platform alongside researchers, developers and data scientists.
• Test, remediate, and harden agentic workloads across cloud and AI-powered platforms.
• Communicate findings clearly to non-technical stakeholders and guide improvements.

Connaissances

Dynamic testing tools

Web app pentesting

LLM/MCP familiarity

Vulnerability research

Outils

Mitre framework

OWASP framework

Description du poste

We’re looking for an experienced red teamer with proven credentials in agentic red teaming to join our advanced product and research team.

What you’ll do

You’ll join the team dedicated to building and developing a tool that dynamically tests and evaluates large language models (LLMs) and their native application context for vulnerabilities.

You’ll be working with seasoned reverse engineers, application pentesters, red teamers, and data scientists, bridging multiple digital disciplines by creating a unique suite that gives our clients the capability to test, remediate, and harden their agentic workloads.

What you’ll bring

• Building or contributing to tools used for dynamic application testing
• Working extensively with open source or proprietary tools used for web and application pentesting
• Actively adopting LLMs and Model Context Protocol (MCP) in automating and enhancing your penetration tests
• Spending time researching agentic vulnerabilities and attending relevant trainings or conferences

To fit right in here at The Tech Collective:

• You should be genuinely curious about new developments within the red teaming domain
• You possess the willingness to tackle new and technical challenges as they arise
• You know how to break down and structure complex assignments and enjoy sharing your knowledge and insights with your team members
• You possess a startup mentality to help drive the innovation and ingenuity of our red team products
• You can cooperate seamlessly with different profiles in a highly diverse team of researchers, developers, consultants, and red teamers

We don’t expect you to know everything – after all, agentic security is a rapidly evolving field! In this role, we’re looking for someone who wants to own, develop, and innovate the product modules related to testing the application context (e.g., API security, cryptographic implementation, broken authentication, RBAC) and supporting infrastructure (e.g., misconfigurations, server-side vulnerabilities) for the agents that we test.

To succeed in this role, your experience and competencies should include:

Professional experience

• A minimum of five years’ progressive experience in enterprise red teaming or offensive research
• A proven track record of web application pentesting with an emphasis on remediation and hardening
• Experience defining and driving product roadmaps for red team tools (not required, but highly valued)
• Demonstrated ability to evaluate complex technology stacks, including common cloud platforms (M365/Azure, Google, or AWS), CI/CD pipelines, and AI-powered platforms and systems
• Experience communicating technical findings to non-technical stakeholders and the ability to bring technical assessments to life

Technical competencies

• Familiarity with both Mitre and OWASP frameworks, and experience applying them in client reporting
• Relevant security certifications (e.g., OSCP, OSCE, OSEP, GIAC GPEN/GXPN, etc.) are a plus, indicating solid foundational knowledge and commitment to the offensive security field.
• Prior experience developing agent-specific attack types such as prompt injection, memory & context poisoning, or jailbreaking
• A working understanding of MCP, LLM pipelines, the functional aspects of LLMs, and how modern agent solutions are integrated with widely used cloud suites such as M365 or AWS

Finally, experience in intermediate to advanced vulnerability research related to applications or operating systems will be considered a strong plus, but is not a requirement for this role.

What we offer

On top of a competitive salary and bonus package, we offer you the opportunity to join a unique team of experts and enthusiasts in your field. Our expectations are matched by our willingness to invest in your development – whether through training, conferences, or the opportunity to pursue research in areas you’re passionate about.

We combine remote work with meaningful co-working at our offices in Copenhagen and will provide you with the tooling and hardware required to reach our goal of building a unique red team platform.

For questions or enquiries, feel free to contact Anders Rømer Skøtt at // .